PrefaceSPSS 16.0 SPSS 16.0 is a comprehensive system for analyzing data. SPSS can take data from almost any type of ﬁle and use them to generate tabulated reports, charts and plots of distributions and trends, descriptive statistics, and complex statistical analyses. This manual, the SPSS Base 16.0 User’s Guide, documents the graphical user interface of SPSS. Examples using the statistical procedures found in SPSS Base 16.0 are provided in the Help system, installed with the software. Algorithms used in the statistical procedures are provided in PDF form and are available from the Help menu. In addition, beneath the menus and dialog boxes, SPSS uses a command language. Some extended features of the system can be accessed only via command syntax. (Those features are not available in the Student Version.) Detailed command syntax reference information is available in two forms: integrated into the overall Help system and as a separate document in PDF form in the SPSS 16.0 Command Syntax Reference, also available from the Help menu.SPSS Options The following options are available as add-on enhancements to the full (not Student Version) SPSS Base system: SPSS Regression Models™ provides techniques for analyzing data that do not ﬁt traditional linear statistical models. It includes procedures for probit analysis, logistic regression, weight estimation, two-stage least-squares regression, and general nonlinear regression. SPSS Advanced Models™ focuses on techniques often used in sophisticated experimental and biomedical research. It includes procedures for general linear models (GLM), linear mixed models, generalized linear models (GZLM), generalized estimating equations (GEE), variance components analysis, loglinear analysis, actuarial life tables, Kaplan-Meier survival analysis, and basic and extended Cox regression. SPSS Tables™ creates a variety of presentation-quality tabular reports, including complex stub-and-banner tables and displays of multiple-response data. SPSS Trends™ performs comprehensive forecasting and time series analyses with multiple curve-ﬁtting models, smoothing models, and methods for estimating autoregressive functions. SPSS Categories® performs optimal scaling procedures, including correspondence analysis. SPSS Conjoint™ provides a realistic way to measure how individual product attributes affect consumer and citizen preferences. With SPSS Conjoint, you can easily measure the trade-off effect of each product attribute in the context of a set of product attributes—as consumers do when making purchasing decisions. iii
SPSS Exact Tests™ calculates exact p values for statistical tests when small or very unevenlydistributed samples could make the usual tests inaccurate.SPSS Missing Value Analysis™ describes patterns of missing data, estimates means and otherstatistics, and imputes values for missing observations.SPSS Maps™ turns your geographically distributed data into high-quality maps with symbols,colors, bar charts, pie charts, and combinations of themes to present not only what is happeningbut where it is happening.SPSS Complex Samples™ allows survey, market, health, and public opinion researchers, as wellas social scientists who use sample survey methodology, to incorporate their complex sampledesigns into data analysis.SPSS Classification Trees™ creates a tree-based classiﬁcation model. It classiﬁes cases into groupsor predicts values of a dependent (target) variable based on values of independent (predictor)variables. The procedure provides validation tools for exploratory and conﬁrmatory classiﬁcationanalysis.SPSS Data Preparation™ provides a quick visual snapshot of your data. It provides the ability toapply validation rules that identify invalid data values. You can create rules that ﬂag out-of-rangevalues, missing values, or blank values. You can also save variables that record individual ruleviolations and the total number of rule violations per case. A limited set of predeﬁned rules thatyou can copy or modify is provided.Amos™ (analysis of moment structures) uses structural equation modeling to conﬁrm and explainconceptual models that involve attitudes, perceptions, and other factors that drive behavior.The SPSS family of products also includes applications for data entry, text analysis, classiﬁcation,neural networks, and predictive enterprise services.InstallationTo install the SPSS Base system, run the License Authorization Wizard using the authorizationcode that you received from SPSS Inc. For more information, see the installation instructionssupplied with the SPSS Base system.CompatibilitySPSS is designed to run on many computer systems. See the installation instructions that camewith your system for speciﬁc information on minimum and recommended requirements.Serial NumbersYour serial number is your identiﬁcation number with SPSS Inc. You will need this serial numberwhen you contact SPSS Inc. for information regarding support, payment, or an upgraded system.The serial number was provided with your Base system. iv
Customer ServiceIf you have any questions concerning your shipment or account, contact your local ofﬁce, listedon the SPSS Web site at http://www.spss.com/worldwide. Please have your serial number readyfor identiﬁcation.Training SeminarsSPSS Inc. provides both public and onsite training seminars. All seminars featurehands-on workshops. Seminars will be offered in major cities on a regular basis. For moreinformation on these seminars, contact your local ofﬁce, listed on the SPSS Web site athttp://www.spss.com/worldwide.Technical SupportThe services of SPSS Technical Support are available to maintenance customers. Customersmay contact Technical Support for assistance in using SPSS or for installation help for oneof the supported hardware environments. To reach Technical Support, see the SPSS Website at http://www.spss.com, or contact your local ofﬁce, listed on the SPSS Web site athttp://www.spss.com/worldwide. Be prepared to identify yourself, your organization, and theserial number of your system.Additional PublicationsAdditional copies of product manuals may be purchased directly from SPSS Inc. Visit the SPSSWeb Store at http://www.spss.com/estore, or contact your local SPSS ofﬁce, listed on the SPSSWeb site at http://www.spss.com/worldwide. For telephone orders in the United States andCanada, call SPSS Inc. at 800-543-2185. For telephone orders outside of North America, contactyour local ofﬁce, listed on the SPSS Web site. The SPSS Statistical Procedures Companion, by Marija Norušis, has been published byPrentice Hall. A new version of this book, updated for SPSS 16.0, is planned. The SPSSAdvanced Statistical Procedures Companion, also based on SPSS 16.0, is forthcoming. TheSPSS Guide to Data Analysis for SPSS 16.0 is also in development. Announcements ofpublications available exclusively through Prentice Hall will be available on the SPSS Web site athttp://www.spss.com/estore (select your home country, and then click Books).Tell Us Your ThoughtsYour comments are important. Please let us know about your experiences with SPSS products. Weespecially like to hear about new and interesting applications using the SPSS Base system. Pleasesend e-mail to firstname.lastname@example.org or write to SPSS Inc., Attn.: Director of Product Planning, 233South Wacker Drive, 11th Floor, Chicago, IL 60606-6412.About This ManualThis manual documents the graphical user interface for the procedures included in the SPSSBase system. Illustrations of dialog boxes are taken from SPSS. Detailed information about thecommand syntax for features in the SPSS Base system is available in two forms: integrated into v
the overall Help system and as a separate document in PDF form in the SPSS 16.0 CommandSyntax Reference, available from the Help menu.Contacting SPSSIf you would like to be on our mailing list, contact one of our ofﬁces, listed on our Web siteat http://www.spss.com/worldwide. vi
Chapter 1Overview SPSS provides a powerful statistical-analysis and data-management system in a graphical environment, using descriptive menus and simple dialog boxes to do most of the work for you. Most tasks can be accomplished simply by pointing and clicking the mouse. In addition to the simple point-and-click interface for statistical analysis, SPSS provides: Data Editor. The Data Editor is a versatile spreadsheet-like system for deﬁning, entering, editing, and displaying data. Viewer. The Viewer makes it easy to browse your results, selectively show and hide output, change the display order results, and move presentation-quality tables and charts to and from other applications. Multidimensional pivot tables. Your results come alive with multidimensional pivot tables. Explore your tables by rearranging rows, columns, and layers. Uncover important ﬁndings that can get lost in standard reports. Compare groups easily by splitting your table so that only one group is displayed at a time. High-resolution graphics. High-resolution, full-color pie charts, bar charts, histograms, scatterplots, 3-D graphics, and more are included as standard features. Database access. Retrieve information from databases by using the Database Wizard instead of complicated SQL queries. Data transformations. Transformation features help get your data ready for analysis. You can easily subset data; combine categories; add, aggregate, merge, split, and transpose ﬁles; and more. Online Help. Detailed tutorials provide a comprehensive overview; context-sensitive Help topics in dialog boxes guide you through speciﬁc tasks; pop-up deﬁnitions in pivot table results explain statistical terms; the Statistics Coach helps you ﬁnd the procedures that you need; Case Studies provide hands-on examples of how to use statistical procedures and interpret the results. Command language. Although most tasks can be accomplished with simple point-and-click gestures, SPSS also provides a powerful command language that allows you to save and automate many common tasks. The command language also provides some functionality that is not found in the menus and dialog boxes. Complete command syntax documentation is integrated into the overall Help system and is available as a separate PDF document, Command Syntax Reference, which is also available from the Help menu. 1
2Chapter 1What’s New in Version 16.0? User interface enhancements. Enhancements to the point-and-click interface include: All dialog boxes are now resizable. The ability to make a dialog box wider makes variable lists wider so that you can see more of the variable names and/or descriptive labels. The ability to make a dialog box longer makes variable lists longer so that you can see more variables without scrolling. Drag-and-drop variable selection is now supported in all dialog boxes. Variable list display order and display characteristics can be changed on the ﬂy in all dialog boxes. Change the sort order (alphabetic, ﬁle order, measurement level) and/or switch between display of variable names or variable labels whenever you want. For more information, see Variable Names and Variable Labels in Dialog Box Lists on p. 6. Data and output management. Data and output management enhancements include: Read and write Excel 2007 ﬁles. Choose between working with multiple datasets or one dataset at a time. For more information, see General Options in Chapter 45 on p. 454. Search and replace information in Viewer documents, including hidden items and layers in multidimensional pivot tables. For more information, see Finding and Replacing Information in the Viewer in Chapter 10 on p. 208. Assign missing values and value labels to any string variable, regardless of the deﬁned string width (previously limited to strings with a deﬁned width of 8 or less bytes). New character-based string functions. Output Management System (OMS) support for Viewer ﬁle format (.spv) and VML-format charts and image maps with pop-up chart information for HTML documents. For more information, see Output Management System in Chapter 48 on p. 484. Customize Variable View in the Data Editor. Change the display order of the attribute columns, and control which attribute columns are displayed. For more information, see Customizing Variable View in Chapter 5 on p. 84. Sort variables in the active dataset alphabetically or by attribute (dictionary) values. For more information, see Sort Variables in Chapter 9 on p. 168. Spell check variable labels and value labels in Variable View. For more information, see Spell Checking Variable and Value Labels in Chapter 5 on p. 85. Change basic variable type (string, numeric), change the deﬁned width of string variables, and automatically set the width of string variables to the longest observed value for each variable. Read and write Unicode data and syntax ﬁles. For more information, see General Options in Chapter 45 on p. 454. Control the default directory location to look for and save ﬁles. For more information, see File Locations Options in Chapter 45 on p. 466. Performance. For computers with multiple processors or processors with multiple cores, multithreading for faster performance is now available for some procedures.
3 OverviewStatistical enhancements. Statistical enhancements include: Partial Least Squares (PLS). A predictive technique that is an alternative to ordinary least squares (OLS) regression, canonical correlation, or structural equation modeling, and it is particularly useful when predictor variables are highly correlated or when the number of predictors exceeds the number of cases. For more information, see Partial Least Squares Regression in Chapter 29 on p. 342. Multilayer perceptron (MLP). The MLP procedure ﬁts a particular kind of neural network called a multilayer perceptron. The multilayer perceptron uses a feed-forward architecture and can have multiple hidden layers. The multilayer perceptron is very ﬂexible in the types of models it can ﬁt. It is one of the most commonly used neural network architectures. This procedure is available in the new Neural Networks option. Radial basis function (RBF). A Radial basis function (RBF) network is a feed-forward, supervised learning network with only one hidden layer, called the radial basis function layer. Like the multilayer perceptron (MLP) network, the RBF network can do both prediction and classiﬁcation. It can be much faster than MLP, however it is not as ﬂexible in the types of models it can ﬁt. This procedure is available in the new Neural Networks option. Generalized Linear Models supports numerous new features, including ordinal multinomial and Tweedie distributions, maximum likelihood estimation of the negative binomial ancillary parameter, and likelihood-ratio statistics. This procedure is available in the Advanced Models option. Cox Regression now provides the ability to export model information to an XML (PMML) ﬁle. This procedure is available in the Advanced Models option. Complex Samples Cox Regression. Apply Cox proportional hazards regression to analysis of survival times—that is, the length of time before the occurrence of an event for samples drawn by complex sampling methods. This procedure supports continuous and categorical predictors, which can be time-dependent. This procedure provides an easy way of considering differences in subgroups as well as analyzing effects of a set of predictors. The procedure estimates variances by taking into account the sample design used to select the sample, including equal probability and probability proportional to size (PPS) methods and with replacement (WR) and without replacement (WOR) sampling procedures. This procedure is available in the Complex Samples option.Programmability extension. Programmability extension enhancements include: R-Plugin. Combine the power of SPSS with the ability to write your own statistical routines with R. This plug-in is available only as a download from www.spss.com/devcentral (http://www.spss.com/devcentral). Nested Begin Program-End Program command structures. Ability to create and manage multiple datasets.Command syntax. For a complete list of command syntax additions and changes, see the ReleaseHistory section of the Introduction chapter in the Command Syntax Reference (available on theHelp menu).
4Chapter 1 Features No Longer Supported There is no longer a separate chart editor for “interactive” charts. Charts created from the legacy “interactive” chart dialog boxes and from IGRAPH command syntax are created in the same format as all other charts and edited in the same chart editor. Some features provided in the legacy “interactive” chart dialog boxes and IGRAPH command syntax are no longer available. The Draft Viewer is no longer available. You cannot open Viewer ﬁles created in previous versions of SPSS (.spo ﬁles) in SPSS 16.0. For Windows operating systems, the installation CD includes a Legacy Viewer that you can install to view and edit Viewer ﬁles created in previous releases. The Maps option is no longer available. Dialog box interfaces for the legacy procedures in the Trends and Tables options are no longer available. For Trends, this includes the following commands: AREG, ARIMA, and EXSMOOTH. For Tables, this includes the TABLES command. If you have a license for either of these options that includes the legacy procedures, command syntax for these commands is still supported.Windows There are a number of different types of windows in SPSS: Data Editor. The Data Editor displays the contents of the data ﬁle. You can create new data ﬁles or modify existing data ﬁles with the Data Editor. If you have more than one data ﬁle open, there is a separate Data Editor window for each data ﬁle. Viewer. All statistical results, tables, and charts are displayed in the Viewer. You can edit the output and save it for later use. A Viewer window opens automatically the ﬁrst time you run a procedure that generates output. Pivot Table Editor. Output that is displayed in pivot tables can be modiﬁed in many ways with the Pivot Table Editor. You can edit text, swap data in rows and columns, add color, create multidimensional tables, and selectively hide and show results. Chart Editor. You can modify high-resolution charts and plots in chart windows. You can change the colors, select different type fonts or sizes, switch the horizontal and vertical axes, rotate 3-D scatterplots, and even change the chart type. Text Output Editor. Text output that is not displayed in pivot tables can be modiﬁed with the Text Output Editor. You can edit the output and change font characteristics (type, style, color, size). Syntax Editor. You can paste your dialog box choices into a syntax window, where your selections appear in the form of command syntax. You can then edit the command syntax to use special features that are not available through dialog boxes. You can save these commands in a ﬁle for use in subsequent sessions.